Published in Proceedings of the VLDB Endowment (VLDB 2027), 2027
To appear. We study transactional data change for real-time analytics in lakehouses.
Recommended citation: Dongyang Geng, Haoqiong Bian, Zinuo Li, and Haoyue Li. (2027). "Transactional Data Change for Real-Time Analytics in Lakehouses." Proceedings of the VLDB Endowment. To appear.
Published in Proceedings of the 1st International Workshop on Data FORMATS for Modern Data Systems (FORMATS'26 @ SIGMOD), 2026
We examine consistency and data freshness trade-offs in lake table formats and lakehouse systems.
Recommended citation: Zinuo Li, Dongyang Geng, Haoyue Li, Hailong Yu, Qi Lei, and Haoqiong Bian. (2026). "How Consistent and Fresh are Lake Tables Really." Proceedings of the 1st International Workshop on Data FORMATS for Modern Data Systems (FORMATS'26 @ SIGMOD).
Download Paper
Published in Proceedings of the 41st IEEE International Conference on Data Engineering (ICDE), Demo, 2025
PixelsDB is an open-source data analytic system that combines a natural-language interface with a serverless query engine offering multiple performance service levels and prices.
Recommended citation: Haoqiong Bian, Dongyang Geng, Haoyang Li, Yunpeng Chai, and Anastasia Ailamaki. (2025). "PixelsDB: Serverless and NL-Aided Data Analytics with Flexible Service Levels and Prices." Proceedings of the 41st IEEE International Conference on Data Engineering (ICDE). 4612–4615.
Download Paper
Published in arXiv preprint arXiv:2409.01388, 2024
We study flexible performance SLAs and prices for serverless query processing, and present PixelsDB, an open-source prototype with three service levels.
Recommended citation: Haoqiong Bian, Dongyang Geng, Panfeng Guo, Yunpeng Chai, and Anastasia Ailamaki. (2024). "Serverless Query Processing with Flexible Performance SLAs and Prices." arXiv preprint arXiv:2409.01388.
Download Paper